Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to bibliographic references and academic citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pio
    -0.19
    ijo
    -0.17
    خاÙĨÙĩ
    -0.15
    irate
    -0.14
    /oct
    -0.14
     loin
    -0.14
    quine
    -0.14
    inde
    -0.14
    unte
    -0.14
    lix
    -0.14
    POSITIVE LOGITS
     est
    0.32
     Est
    0.22
    Est
    0.21
    .est
    0.20
    est
    0.20
     EST
    0.20
    _est
    0.19
    ’est
    0.19
    (est
    0.18
     estimator
    0.18
    Act Density 0.003%

    No Known Activations